Digitalni repozitorijum
Univerziteta u Beogradu
{{ mc.sd.lang | uppercase }}
Challenges in applying machine learning for predictive modelling
Tešić, Nataša
Mitrašević, Mirela
Bradić, Kristina
The rapid evolution of digital financial transactions and insurance operations has significantly increased the reliance on machine learning for predictive modelling. The application of sophisticated machine learning techniques, including feature transformation, data balancing, and model optimisation, enabled the detection of anomalies in financial systems and claim predictions in the insurance sector. Assuming that artificial intelligence (AI) can contribute to the improvement of the actuarial profession in the Republic of Srpska, this chapter of the monograph will, along with discussing its application in predicting claims and assessing insurance risk, also present the prerequisites that artificial intelligence needs to fulfil to be utilised in the insurance market of the Republic of Srpska while following ethical standards and actuarial practice guidelines. Our aim is to explore the potential impacts of artificial intelligence on the actuarial profession, analysing how actuaries can use AI tools and techniques to enhance their work and competencies and, thus, provide benefits to policyholders, insurers, and the development of this profession.
This research is supported by the Ministry of Scientific and Technological Development and Higher Education of the Republika Srpska under the Agreement on Co-financing of the Scientific and Research Project, No. 19.032/961-46/24 of 30. December 2024.
engleski
2025
Ovo delo je licencirano pod uslovima licence
Creative Commons CC BY-NC-ND 4.0 - Creative Commons Autorstvo - Nekomercijalno - Bez prerada 4.0 International License.
http://creativecommons.org/licenses/by-nc-nd/4.0/legalcode
Key words: insurance market, Republika Srpska, AI, machine learning
170430729